Image-Processing-Based Low-Cost Fault Detection Solution for End-of-Line ECUs in Automotive Manufacturing

Abstract

The manufacturing industry is continuously researching and developing strategies and solutions to increase product quality and to decrease production time and costs. The approach is always targeting more automated, traceable, and supervised production, minimizing the impact of the human factor. In the automotive industry, the Electronic Control Unit (ECU) manufacturing ends with complex testing, the End-of-Line (EoL) products being afterwards sent to client companies. This paper proposes an image-processing-based low-cost fault detection (IP-LC-FD) solution for the EoL ECUs, aiming for high-quality and fast detection. The IP-LC-FD solution approaches the problem of determining, on the manufacturing line, the correct mounting of the pins in the locations of each connector of the ECU module, respectively, other defects as missing or extra pins, damaged clips, or surface cracks. The IP-LC-FD system is a hardware–software structure, based on Raspberry Pi microcomputers, Pi cameras, respectively, Python and OpenCV environments. This paper presents the two main stages of the research, the experimental model, and the prototype. The rapid integration into the production line represented an important goal, meaning the accomplishment of the specific hard acceptance requirements regarding both performance and functionality. The solution was implemented and tested as an experimental model and prototype in a real industrial environment, proving excellent results.

Approaching OPC UA Publish–Subscribe in the Context of UDP-Based Multi-Channel Communication and Image Transmission

“…The final case study 3 scenario is oriented toward a previous step within the EOL testing of ECUs in the automotive manufacturing, the automatic optical boards inspection, detecting ECU defects at pins, clips, or surface cracks [ 11 ]. The results of [ 11 ] present the image processing-based detection of defects realized within 6.5 s. The passed/failed bit result is transmitted to the MES under the required time limit.…”

“…In the automotive manufacturing industry, image processing is frequently used. As exemplified in [ 11 ], during the manufacturing of ECU boards, automatic optical inspection (AOI) is performed at the end-of-line testing and packaging. Referring strictly to the end-of-line testing and packaging, tens of thousands of products are tested daily in a company using image processing for various defects, and the packaging process is also assured using image processing.…”

“…In [ 10 ], the authors approached an image-processing solution and deep learning to detect deformation on pantograph contact strip of railway vehicles. In [ 11 ], the authors presented a low-cost image-processing solution based on Open-Source Computer Vision Library (OpenCV) that is used to detect defects in automotive parts manufacturing, particularly defects as faulty, missing, or extra pins, faulty clips, board cracks, and electronic control units (ECUs). Most studies are considering that the industrial process and the image transmission as separate fractions.…”

Improving OPC UA Publish-Subscribe Mechanism over UDP with Synchronization Algorithm and Multithreading Broker Application

“…The manufacturing industry in general and also other industries could benefit by using the current concept. Considering an example of the end-of-line automotive manufacturing testing and packing, where a machine realizes automated optical inspection for ECU pins [ 26 ], after robotic pins insertion on boards, enclosure fixing and labeling, and before transporting and packing into boxes and final optical inspection of counting boards in boxes for sending to client companies. The automatic optical inspection (AOI) structure has to finalize the whole image processing in seconds and it has to communicate with the PLC on the same machine that fixes the enclosure, rotates the structure, and sends the ECU for packing or to part disposal.…”

Switchable Glass Enabled Contextualization for a Cyber-Physical Safe and Interactive Spatial Augmented Reality PCBA Manufacturing Inspection System

“…The inspection of PCBAs is regularly performed during and after manufacturing assembly to ensure proper parts are correctly localized on right boards [ 2 ]. This inspection is often undertaken through automatic optical inspection (AOI) machines [ 3 ] complemented by high-skill inspectors. The inspector is required to verify whether the defects previously identified and localized by an AOI system could affect the PCBA’s functionality upon product completion.…”